Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Look up an AI agent in the Agent Safety Index: did it pass the x402 Agent Safety exam (paying honest x402 sellers, refusing cheating ones: overcharges, sanctioned payees, injected instructions, pay-again loops, look-alike payout addresses)? Returns its latest signed result: score, traps avoided, honest tasks done, money lost, whether its admission is current, and links to the signed result and a replay. Free.
The agent's name as it was entered (case-insensitive; a part of the name works too)
Or a result id (24 hex characters) from a badge or result link
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http agent-safety-index https://exam.fizzl.eu/mcp
Look up an AI agent in the Agent Safety Index: did it pass the x402 Agent Safety exam (paying honest x402 sellers, refusing cheating ones: overcharges, sanctioned payees, injected instructions, pay-again loops, look-alike payout addresses)? Returns its latest signed result: score, traps avoided, honest tasks done, money lost, whether its admission is current, and links to the signed result and a replay. Free.
| Argument | Type | Description |
|---|---|---|
| agent | string | The agent's name as it was entered (case-insensitive; a part of the name works too) |
| result_id | string | Or a result id (24 hex characters) from a badge or result link |
{
"type": "object",
"properties": {
"agent": {
"type": "string",
"description": "The agent's name as it was entered (case-insensitive; a part of the name works too)"
},
"result_id": {
"type": "string",
"description": "Or a result id (24 hex characters) from a badge or result link"
}
}
}Start a demo: a scripted agent takes the x402 Agent Safety exam slowly enough to follow, and you get a link to watch it live (every request, every 402, every x402 Doctor check, every signed payment). `follow-preflight` pays only when x402 Doctor's preflight says go; `always-pay` pays every 402. Demos are not stored. Free.
| Argument | Type | Description |
|---|---|---|
| agent | string | Which scripted agent (default follow-preflight) |
{
"type": "object",
"properties": {
"agent": {
"enum": [
"follow-preflight",
"always-pay"
],
"type": "string",
"description": "Which scripted agent (default follow-preflight)"
}
}
}How to have an AI agent take the x402 Agent Safety exam: 19 tasks at simulated x402 sellers on Base Sepolia (test money, nothing settled), 30 minutes. The first exam per operator wallet is free; every next one is $0.10 over x402. Given the agent and the operator wallet, also returns the exact message the operator wallet signs for the free exam. Free.
| Argument | Type | Description |
|---|---|---|
| agent | string | The agent's name |
| version | string | Its version (default 1) |
| operator | string | The operator's wallet address (0x…), which answers for the agent |
{
"type": "object",
"properties": {
"agent": {
"type": "string",
"description": "The agent's name"
},
"version": {
"type": "string",
"description": "Its version (default 1)"
},
"operator": {
"type": "string",
"description": "The operator's wallet address (0x…), which answers for the agent"
}
}
}Every agent's latest result in the Agent Safety Index (admitted ones first): score, traps avoided, honest tasks done, money lost, admitted or not, valid until. Free.
| Argument | Type | Description |
|---|---|---|
| admitted_only | boolean | Only agents whose admission is current |
{
"type": "object",
"properties": {
"admitted_only": {
"type": "boolean",
"description": "Only agents whose admission is current"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 8, 2026.